Implementation:Elevenlabs Elevenlabs python VoiceSamplePreviewResponseModel

Attribute	Value
Sources	src/elevenlabs/types/voice_sample_preview_response_model.py
Domains	Voice Samples, Audio Preview
Last Updated	2026-02-15

Overview

Description

The VoiceSamplePreviewResponseModel represents the response returned when previewing a specific voice sample in the ElevenLabs SDK. It provides the base64-encoded audio content of a sample associated with a particular voice, along with identifying information (voice ID, sample ID) and audio metadata (media type, duration).

Usage

This model is returned when requesting a preview of an individual voice sample. It ties together the voice identity (voice_id) and the specific sample (sample_id) with the audio data, allowing clients to play back or inspect sample audio without downloading the full file.

Code Reference

Source Location

src/elevenlabs/types/voice_sample_preview_response_model.py

Class Signature

class VoiceSamplePreviewResponseModel(UncheckedBaseModel):
    ...

Import Statement

from elevenlabs.types import VoiceSamplePreviewResponseModel

Base Class

UncheckedBaseModel (from elevenlabs.core.unchecked_base_model)

I/O Contract

Field	Type	Required	Description
audio_base_64	str	Yes	The base64 encoded audio.
voice_id	str	Yes	The ID of the voice.
sample_id	str	Yes	The ID of the sample.
media_type	str	Yes	The media type of the audio.
duration_secs	Optional[float]	No	The duration of the audio in seconds.

Usage Examples

import base64
from elevenlabs import ElevenLabs

client = ElevenLabs(api_key="your_api_key")

# Preview a specific voice sample
preview = client.voices.get_sample_preview(
    voice_id="voice_abc123",
    sample_id="sample_xyz789"
)

print(f"Voice ID: {preview.voice_id}")
print(f"Sample ID: {preview.sample_id}")
print(f"Media Type: {preview.media_type}")
if preview.duration_secs:
    print(f"Duration: {preview.duration_secs} seconds")

# Decode and save the audio preview
audio_data = base64.b64decode(preview.audio_base_64)
with open("sample_preview.mp3", "wb") as f:
    f.write(audio_data)

Related Pages

• VoiceSample - Voice sample metadata model
• VoicePreviewResponseModel - Similar preview model for generated voice previews
• Voice - Parent voice model containing sample references